Search Images Maps Play YouTube News Gmail Drive More »
Sign in
Screen reader users: click this link for accessible mode. Accessible mode has the same essential features but works better with your reader.

Patents

  1. Advanced Patent Search
Publication numberUS6539376 B1
Publication typeGrant
Application numberUS 09/440,626
Publication date25 Mar 2003
Filing date15 Nov 1999
Priority date15 Nov 1999
Fee statusLapsed
Publication number09440626, 440626, US 6539376 B1, US 6539376B1, US-B1-6539376, US6539376 B1, US6539376B1
InventorsNeelakantan Sundaresan, Jeonghee Yi
Original AssigneeInternational Business Machines Corporation
Export CitationBiBTeX, EndNote, RefMan
External Links: USPTO, USPTO Assignment, Espacenet
System and method for the automatic mining of new relationships
US 6539376 B1
Abstract
An automatic mining system that identifies a set of relevant terms from a large text database of unstructured information, such as the World Wide Web with a high degree of confidence. The automatic mining system includes a software program that enables the discovery of new relationships by association mining and refinement of co-occurrences, using automatic and iterative recognition of new binary relations through phrases that embody related pairs, by applying lexicographic and statistical techniques to classify the relations, and further by applying a minimal amount of domain knowledge of the relevance of the terms and relations. The automatic mining system includes a knowledge module and a statistics module. The knowledge module is comprised of a stemming unit, a synonym check unit, and a domain knowledge check unit. The stemming unit determines if the relation being analyzed shares a common root with a previously mined relation. The synonym check unit identifies the synonyms of the relation, and the domain knowledge check unit considers extrinsic factors for indications that would further clarify the relationship being mined. The statistics module optimizes the confidence level in the relationship.
Images(6)
Previous page
Next page
Claims(21)
What is claimed is:
1. A system of automatically mining a new relationship for an extracted pair pi and a relation ri within a document di, comprising:
a relations database for storing previously identified sets of pairs Pi−1 and relations Ri−1;
a relations database for storing previously identified sets of pairs Pi−1 and relations Ri−1;
a relationship database for storing the relation ri under a corresponding relationship category;
wherein if there is no relationship category corresponding to the relation ri in the relationship database, a knowledge module receives the extracted pair pi and the relation ri and applies a linguistic technique to classify the relation ri;
wherein if the linguistic technique fails to identify a corresponding relationship category in the relationship database, a statistics module receives the relation ri and applies a statistical technique to classify the relation ri; and
wherein if the statistical technique fails to identity a corresponding relationship category in the relationship database, defining a new relationship category and storing the relation ri under the new relationship category in the relationship database.
2. The system according to claim 1, wherein the knowledge module includes a stemming unit that determines if the relation ri shares a common root with a previously mined relation ri−1 in the relations database.
3. The system according to claim 2, wherein the knowledge module includes a synonym check unit that identifies one or more synonyms of the relation ri.
4. The system according to claim 2, wherein the knowledge module includes a domain knowledge check unit that considers one or more extrinsic indications to clarify the new relationship.
5. The system according to claim 1, wherein the knowledge module includes:
a stemming unit that determines if the relation ri shares a common root with a previously mined relation ri−1 in the database;
a synonym check unit that identifies one or more synonyms of the relation ri;
a domain knowledge check unit that considers one or more extrinsic indications to clarify the new relationship.
6. The system according to claim 1, wherein the knowledge module includes a stemming unit that determines if the relation ri shares a common root with a previously mined relation ri−1 in the database, and removes common suffixes, if any.
7. The system according to claim 1, wherein the linguistic technique comprises stemming.
8. The system according to claim 7, wherein the linguistic technique further comprises synonym checking.
9. The system according to claim 1, wherein the knowledge module further applies domain knowledge to classify the relation ri.
10. A computer program product of automatically mining a new relationship for an extracted pair pi and a relation ri within a document di, comprising:
a relations database for storing previously identified sets of pairs Pi−1 and relations Ri−1;
a relations database for storing previously identified sets of pairs Pi−1 and relations Ri−1;
a relationship database for storing the relation ri under a corresponding relationship category;
wherein if there is no relationship category corresponding to the relation ri in the relationship database, a knowledge module receives the extracted pair pi and the relation ri and applies a linguistic technique to classify the relation ri;
wherein if the linguistic technique fails to identify a corresponding relationship category in the relationship database, a statistics module receives the relation ri and applies a statistical technique to classify the relation ri; and
wherein if the statistical technique fails to identify a corresponding relationship category in the relationship database, defining a new relationship category and storing the relation ri under the new relationship category in the relationship database.
11. The computer program product according to claim 10, wherein the knowledge module includes a stemming unit that determines if the relation ri shares a common root with a previously mined relation ri−1 in the relations database.
12. The computer program product according to claim 11, wherein the knowledge module includes a synonym check unit that identifies one or more synonyms of the relation ri.
13. The computer program product according to claim 11, wherein the knowledge module includes a domain knowledge check unit that considers one or more extrinsic indications to clarify the new relationship.
14. The computer program product according to claim 10, wherein the knowledge module includes:
a stemming unit that determines if the relation ri shares a common root with a previously mined relation ri−1 in the database;
a synonym check unit that identifies one or more synonyms of the relation ri;
a domain knowledge check unit that considers one or more extrinsic indications to clarify the new relationship.
15. The computer program product according to claim 10, wherein the knowledge module includes a stemming unit that determines if the relation ri shares a common root with a previously mined relation ri−1 in the database, and removes common suffixes, if any.
16. A method of automatically mining a new relationship for an extracted pair pi and a relation ri within a document di, comprising:
a relations database storing previously identified sets of pairs Pi−1 and relations Ri−1;
a relationship database storing the relation ri under a corresponding relationship category;
wherein if there is no relationship category corresponding to the relation ri in the relationship database, a knowledge module receiving the extracted pair pi and the relation ri and applying a linguistic technique to classify the relation ri;
wherein if the linguistic technique fails to identify a corresponding relationship category in the relationship database, a statistics module receiving the relation ri and applies a statistical technique to classify the relation ri; and
wherein if the statistical technique fails to identify a corresponding relationship category in the relationship database, defining a new relationship category and storing the relation ri under the new relationship category in the relationship database.
17. The method according to claim 16, further including determining if the relation ri shares a common root with a previously mined relation ri−1 in the relations database.
18. The method according to claim 17, further including identifying one or more synonyms of the relation ri.
19. The method according to claim 17, further including considering one or more extrinsic indications to clarify the new relationship.
20. The method according to claim 16, further including:
determining if the relation ri shares a common root with a previously mined relation ri−1 in the relations database;
identifying one or more synonyms of the relation ri; and
considering one or more extrinsic indications to clarify the new relationship.
21. The method according to claim 16, further including determining if the relation ri shares a common root with a previously mined
Description
CROSS-REFERENCE TO RELATED APPLICATIONS

This application relates to co-pending U.S. patent applications Ser. No. 09/440,625, titled “System and Method for the Automatic Mining of Acronym-expansion Pairs Patterns and Formation Rules”, Ser. No. 09/439,379, titled “System and Method for the Automatic Mining of Patterns and Relations”, Ser. No. 09/440,203, titled “System and Method the Automatic Construction of Generalization—Specialization Hierarchy of Terms”, Ser. No. 09/440,602, titled “System and Method for the Automatic Recognition of Relevant Terms by Mining Link Annotations”, and Ser. No. 09/439,758, titled “System and Method for the Automatic Discovery of Relevant Terms from the World Wide Web”, all of which are assigned to, and were filed by the same assignee as this application on even date herewith, and are incorporated herein by reference in their entirety.

FIELD OF THE INVENTION

The present invention relates to the field of data mining, and particularly to a software system and associated method for identifying relevant terms from a large text database of unstructured information, such as the World Wide Web (WWW). More specifically, the present invention relates to the automatic and iterative recognition of new binary relations through phrases that embody related pairs, by applying lexicographic and statistical techniques to classify the relations, and further by applying a minimal amount of domain knowledge of the relevance of the terms and relations.

BACKGROUND OF THE INVENTION

The World Wide Web (WWW) is a vast and open communications network where computer users can access available data, digitally encoded documents, books, pictures, and sounds. With the explosive growth and diversity of WWW authors, published information is oftentimes unstructured and widely scattered. Although search engines play an important role in furnishing desired information to the end users, the organization of the information lacks structure and consistency. Web spiders crawl web pages and index them to serve the search engines. As the web spiders visit web pages, they could look for, and learn pieces of information that would otherwise remain undetected.

Current search engines are designed to identify pages with specific phrases and offer limited search capabilities. For example, search engines cannot search for that relate in a particular way, such as books and authors. Bibliometrics involves the study of the world of authorship and citations. It measures the co-citation strength, which is a measure of the similarity between two technical papers on the basis of their common citations. Statistical techniques are used to compute this measures. In typical bibliometric situations the citations and authorship are explicit and do not need to be mined. One of the limitations of the bibliometrics is that it cannot be used to extract buried information in the text.

Exemplary bibliometric studies are reported in: R. Larson, “Bibliometrics of the World Wide Web: An Exploratory Analysis of the Intellectual Structure of Cyberspace,” Technical report, School of Information Management and Systems, University of California, Berkeley, 1996. <http://sherlock.sims.berkeley.edu/docs/asis96/asis96.html>; K. McCain, “Mapping Authors in Intellectual Space: A technical Overview,” Journal of the American Society for Information Science, 41(6):433-443, 1990. A Dual Iterative Pattern Relation Expansion (DIPRE) method that addresses the problem of extracting (author, book) relationships from the web is described in S. Brin, “Extracting Patterns and Relations from the World Wide Web,” WebDB, Valencia, Spain, 1998.

Another area to identify a set of relevant information on the World Wide Web is the Hyperlink-Induced Topic Search (HITS). HITS is a system that identifies authoritative web pages on the basis of the link structure of web pages. It iteratively identifies good hubs, that is pages that point to good authorities, and good authorities, that is pages pointed to by good hub pages. This technique has been extended to identify communities on the web, and to target a web crawler. One of HITS' limitations resides in the link topology of the pattern space, where the hubs and the authorities are of the same kind. i.e., they are all web pages. HITS is not defined in the text of web pages in the form of phrases containing relations in specific patterns.

Exemplary HITS studies are reported in: D. Gibson et al., “Inferring Web Communities from Link Topology,” HyperText, pages 225-234, Pittsburgh, Pa., 1998; J. Kleinberg, “Authoritative Sources in a Hyperlinked Environment,” Proc. of 9th ACM-SIAM Symposium on Discrete Algorithms, May 1997; R. Kumar, “Trawling the Web for Emerging Cyber-Communities,” published on the WWW at URL: <http://www8.org/w8-papers/4a-search-mining/trawling/trawling.html>as of Nov. 13, 1999; and S. Chakrabarti et al. “Focused Crawling: A New Approach to Topic-Specific Web Resource Discovery,” Proc. of The 8th International World Wide Web Conference, Toronto, Canada, May 1999.

Furthermore, not only is the quantity of WWW material increasing, but the types of digitized material are also increasing. For example, it is possible to store alphanumeric texts, data, audio recordings, pictures, photographs, drawings, images, video and prints. However, such large quantities of materials is of little value unless it the desired information is readily retrievable. While, as discussed above, certain techniques have been developed for accessing certain types of textual materials, these techniques are at best moderately adequate for accessing graphic, audio or other specialized materials. Consequently, there are large bodies of published materials that remain inaccessible and thus unusable or significantly under utilized.

A common technique for accessing textual materials is by means of a “keyword” combination, generally with boolean connections between the words or terms. This searching technique suffers from several drawbacks. First, the use of this technique is limited to text and is not usable for other types of material. Second, in order to develop a searchable database of terms, the host computer must usually download the entire documents, which is a time-consuming process, and does not normally provide an association between relevant rerms.

Exemplary work in scalable data mining technology, is described in the following references: R. Agrawal et al., “Mining Association Rules Between Sets of Items in Large Databases, Proceedings of ACM SIGMOD Conference on Management of Data, pp. 207-216, Washington, D.C., May 1993; R. Agrawal et al., “Fast Algorithms for Mining Association Rules,” Proc. of the 20th Int'l Conference on VLDB, Santiago, Chile, September 1994; and S. Brin, “Extracting Patterns and Relations from the World Wide Web,” WebDB, Valencia, Spain, 1998, supra. Such work has been successfully applied to identify co-occurring patterns in many real world problems including market basket analysis, cross-marketing, store layout, and customer segmentation based on buying patterns.

Early work on applying association to texts can be found in FACT system, described in R. Feldman et al., “Mining Associations in Text in the Presence of Background Knowledge,” Proceedings of the Second International Conference on Knowledge Discovery and Data Mining, Aug. 2-4, 1996, Portland, Oreg. It discovers associations amongst only keywords representing the topics of the document. The FACT system assumes that a set of predefined keywords describing the document is available. Such an assumption might not be too unrealistic for a set of well annotated documents or for a classes of documents for which text categorization system automatically produces reasonably good annotations with keywords. However, the assumption generally does not hold true for WWW pages since a major portion of the WWW pages is not well annotated. Annotation of the WWW pages by general text categorization techniques can perform poorly, in that these techniques use natural language processing (NLP) that expect grammatically correct sentences, and WWW pages frequently consist of irregular sentences.

There is therefore a great and still unsatisfied need for a software system and associated methods for automatically identifying relevant terms on the World Wide Web. The system and methods should enable the automatic and iterative recognition of binary relations through phrases that embody related pairs, by applying lexicographic and statistical techniques to classify the relations, and further by applying a minimal amount of domain knowledge of the relevance of terms and relations.

SUMMARY OF THE INVENTION

In accordance with the present invention, a computer program product is provided as an automatic mining system to identify a set of related terms from a large text database of unstructured information, such as the World Wide Web (WWW), with a high degree of confidence.

The automatic mining system includes a software program that enables the discovery of new relationships by association mining and refinement of co-occurrences, using automatic and iterative recognition of new binary relations through phrases that embody related pairs, by applying lexicographic and statistical techniques to classify the relations, and further by applying a minimal amount of domain knowledge of the relevance of the terms and relations.

The foregoing and other features and advantages of the present invention can be accomplished by an automatic mining system that includes a database for storing the mined sets of relevant terms and relations, and a software package comprised of a knowledge module and a statistics module. Using the document di, the previously identified sets of pairs Pi−1, and relations Ri−1, the knowledge module inquires whether or not the relation ri exists in the set of relations Ri−1. If the relation ri is deemed not to exist in the set of relations Ri−1, the knowledge module forwards the pair pi and the derived relation ri to the statistics module for optimizing and increasing the confidence level in the relation ri being considered. The derived relation ri is stored in the database for recognizing additional pairs pi+1, and relations ri+1. If the knowledge module determines the relation exists in the set of relations Ri−1, the knowledge module terminates the mining progress and proceeds to mine additional pairs and relations.

In one embodiment, the knowledge module includes one or more of the following units: a stemming unit, a synonym check unit, and a domain knowledge check unit. The stemming unit determines if the relation ri being analyzed shares a common root with a previously mined relation ri−1 in the database. The synonym check unit identifies the synonyms of the relation ri. The domain knowledge check unit considers the content of the document di for indications that would further clarify the relationship of the relations being mined. The statistics module optimizes and increases the confidence level in the relationship on the basis of the previous usage of the relations.

BRIEF DESCRIPTION OF THE DRAWINGS

The various features of the present invention and the manner of attaining them will be described in greater detail with reference to the following description, claims, and drawings, wherein reference numerals are reused, where appropriate, to indicate a correspondence between the referenced items.

FIG. 1 is a schematic illustration of an exemplary operating environment in which the automatic mining system of the present invention can be used.

FIG. 2 is a high level diagram of the automatic mining system of FIG. 1.

FIG. 3 is a more detailed diagram of the automatic mining system of FIG. 2.

FIG. 4 is a flow chart that illustrates the operation of a preferred embodiment of the automatic mining system of FIG. 3.

FIG. 5 is an illustration of two exemplary databases: a relations database and a relationship database, forming part of the automatic mining system of FIG. 2.

DETAILED DESCRIPTION OF THE INVENTION

The following definitions and explanations provide background information pertaining to the technical field of the present invention, and are intended to facilitate the understanding of the present invention without limiting its scope:

Crawler or spider: A program that automatically explores the World Wide Web by retrieving a document and recursively retrieving some or all the documents that are linked to it.

Gateway: A standard interface that specifies how a web server launches and interacts with external programs (such as a database search engine) in response to requests from clients.

Hypertext System: A computer-based informational system in which documents (and possibly other types of data entities) are linked together via hypertext links to form a user-navigable web.

Hypertext Link (or hyperlink): A reference link from some point in one hypertext document to another point in another document or another place in the same document. When a user activates the link (e.g. by clicking on it with the mouse) the browser will display the destination of the link.

HTML (Hypertext Markup Language): A standard language for attaching presentation and linking attributes to informational content within documents. During a document authoring stage, HTML “tags” are embedded within the informational content of the document. When the web document (or “HTML document”) is subsequently transmitted by a web server to a web browser, the tags are interpreted by the browser and used to parse and display the document. In addition to specifying how the web browser is to display the document, HTML tags can be used to create hyperlinks to other web documents.

HTTP (Hypertext Transfer Protocol): Standard WWW client-server protocol used for the exchange of information (such as HTML documents, and client requests for such documents) between a web browser and a web server. HTTP includes several different types of messages that can be sent from the client to the server to request different types of server actions.

Internet: A collection of interconnected public and private computer networks that are linked together with routers by a set of standards protocols to form a global, distributed network.

Metadata (or annotation) of a hyperlink: Description of a hyperlink provided by the page that contains it. Ideally, it describes the concept of the linked page. This description may be found, for example, in elements around a hyperlink's anchor tags. Such elements may include attribute values or free text surrounding the hyperlink. Of these elements, anchor texts seem to be the most descriptive and frequent, and are believed to constitute serious candidates for use as annotations.

Server: A software program or a computer that responds to requests from a web browser by returning (“serving”) web documents.

SGML (Standard Generalized Markup Language): A generic markup language for representing documents. SGML is an International Standard that describes the relation between a document's content and its structure. SGML allows document-based information to be shared and re-used across applications and computer platforms in an open, vendor-neutral format. SGML is defined in “ISO 8879:1986 Information processing—Text and office systems—Standard Generalized Markup Language (SGML)”, an ISO standard produced by JTC 1/SC 18 and amended by “Amendment 1:1 988”.

URL (Uniform Resource Locator): A unique address which fully specifies the location of a content object on the Internet. The general format of a URL is protocol://server-address/path/filename.

XML (Extensible Markup Language): A meta-language that provides a framework (or set of rules) to specify domain specific languages. Sometimes described as a simplified dialect of SGML suitable for use on the Word-Wide Web, it gives rise to such markup languages as SMIL (Synchronized Multimedia Integration Language), CML (Chemical Markup Language), MML (Mathematics Markup Language), etc.

Web browser: A software program that allows users to request and read hypertext documents. The browser gives some means of viewing the contents of web documents and of navigating from one document to another.

Web document or page: A collection of data available on the World Wide Web and identified by a URL. In the simplest, most common case, a web page is a file written in HTML and stored on a web server. It is possible for the server to generate pages dynamically in response to a request from the user. A web page can be in any format that the browser or a helper application can display. The format is transmitted as part of the headers of the response as a MIME type, e.g. “text/htmI”, “image/gif”. An HTML web page will typically refer to other web pages and Internet resources by including hypertext links.

Web Site: A database or other collection of inter-linked hypertext documents (“web documents” or “web pages”) and associated data entities, which is accessible via a computer network, and which forms part of a larger, distributed informational system such as the WWW. In general, a web site corresponds to a particular Internet domain name, and includes the content of a particular organization. Other types of web sites may include, for example, a hypertext database of a corporate “intranet” (i.e., an internal network which uses standard Internet protocols), or a site of a hypertext system that uses document retrieval protocols other than those of the WWW.

World Wide Web (WWW): An Internet client—server hypertext distributed information retrieval system.

FIG. 1 portrays the overall environment in which automatic mining system 10 according to the present invention can be used. The automatic mining system 10 includes a software or computer program product which is typically embedded within, or installed on a host server 15. Alternatively, the automatic mining system 10 can be saved on a suitable storage medium such as a diskette, a CD, a hard drive, or like devices. The cloud-like communication network 20 is comprised of communication lines and switches connecting servers such as servers 25, 27, to gateways such as gateway 30. The servers 25, 27 and the gateway 30 provide the communication access to the WWW Internet. Users, such as remote internet users are represented by a variety of computers such as computers 35, 37, 39, and can query the automatic mining system 10 for the desired information.

The host server 15 is connected to the network 20 via a communications link such as a telephone, cable, or satellite link. The servers 25, 27 can be connected via high speed Internet network lines 44, 46 to other computers and gateways. The servers 25, 27 provide access to stored information such as hypertext or web documents indicated generally at 50, 55, 60. The hypertext documents 50, 55, 60 most likely include embedded hypertext links to other locally stored pages, and hypertext links 70, 72, 74, 76 to other webs sites or documents 55, 60 that are stored by various web servers such as the server 27.

The automatic mining system 10 will now be described with further reference to FIG. 2. The automatic mining system 10 includes a computer program product such as a software package, which is generally comprised of a relations database 80, a knowledge module 90, and a statistics module 100, and a relationship database 130. In an alternative design, the relations database 80 and/or the relationship database 130 do not form part of the automatic mining system 10.

The relations database 80 stores the sets of previously identified inter-related Pi−1 and relations Ri−1, and the relationship database 130 stores the relationships that are mined by the automatic mining system 10. Initially, the relations database 80 begins with small seed sets of pairs P0 and relations R0 that are continuously and iteratively broadened by the automatic mining system 10, as it will be explained in greater detail.

Having described the main components of the automatic mining system 10, its operation will now be described with further reference to FIGS. 3, 4 and 5. As used herein, a “relation” ri is defined as the phrase that connects the components or terms in the pair, a “pair” pi is comprised of two inter-related terms, such as concepts, items, persons and similar entities, and a “relationship” is the category or classification of the relations.

With reference to FIG. 5, the first relation r0 corresponds to the initial seed pair p0 comprised of an employee (Neel San) and an employer (IBM). In this illustration, the seed relation r0 for the seed pair p0 is that of an employee-employer, and is expressed by the phrase “employed by”. The seed relation r0 is categorized and stored in the relationship database 130 under the “Employment Relationship”. Another seed pair p1 is comprised of an employee (John Davis) and an employer (HP), with the relation r1 expressed by the phrase “works for” and stored under the “Employment Relationship”. Yet another seed pair p2 is comprised of a student (Jeonghee Kim) and a school (UCLA), with the relation r2 expressed by the phrase “student at” and stored under the “Student Relationship”.

The automatic mining system 10 provides the added flexibility of allowing a pair pi to be associated with one or more relations ri and classified under one or more relationships. As an illustration, the pair (John Davis, HP) is associated with the relations “works for” and “consultant for”, and is classified under the “Employment Relationship” and the “Consulting Relationship”, respectively.

In the exemplary embodiment illustrated in FIG. 2, a crawler that resides in the host server 15, visits and downloads every page on the Www at periodic intervals, for example about once a month. During a visit to a web page or document di, the crawler downloads the document content to the host server 15. The host server 15 forwards the document di to a system for the automatic mining of patterns and relations 135, which is described for example in the patent application Ser. No. 09/439,379, titled “System and Method for Automatic Mining of Patterns and Relations”. The system 135 derives the relations ri from the document di, and stores the terms or pairs pi and the corresponding relations ri in the relations database 80 within the sets of pairs Pi−1 and relations Ri−1, respectively.

Using the sets of pairs Pi−1 and relations Ri−1 stored in the relations database 80, the knowledge module 90 inquires whether or not the relation ri has been previously categorized under an existing relationship, records the decision in the relationship database 130, and does not consider the relation ri any further. If the knowledge module 90 determines that the relation ri has not been categorized, it forwards the pair pi and the new relation ri to the statistics module 100 for an additional possibility of categorizing the pair pi and the relation ri on the basis of previous statistics. If the statistics module 100 cannot associate the relation ri with an existing relationship, it creates a new relationship for ri. The derived relationships are stored in the relationship database 130.

With further reference to FIG. 3, the knowledge module 90 may include one or more of the following units: a stemming unit 140, a synonym check unit 150, and a domain knowledge check unit 160. It should be clear that the processing order of the information is not limited to the example described herein, and that the knowledge module 90 can process the information in any desired order.

The stemming unit 140 determines if the relation ri shares a common root with a relation ri−1 stored in the relations database 80. For example, the stemming unit 140 removes common suffixes such as “s”, “ing”, or “ed”, that indicate plurality, conjugation, or verb tense, respectively, and retains only the root of the term. The content terms after stemming is used to determine the relation. As an illustration, the terms “employee”, “employer”, “employing”, and “employed” all share the common root “employ”, and are converted to such common root after stemming and are classified under the “Employment Category” (FIG. 5). The stemming unit 140 can be any of the available applications. One such application is available on the WWW at URL: <http:/www.cogsci.princeton.edu/˜wn/>.

The synonym check unit 150 identifies the synonyms of the relation ri being analyzed. The synonym check unit 150 can incorporate or use, one or more applications such as WordNet which is available on the WWW at the following URL: <http://www.cogsci.princeton.edu/˜wn/>, or Webster which is available on the WWW at the following URL: <http://work.ucsd.edu:5141/cgi_bin/http_webster>, English Thesaurus such as Wordsmyth English Dictionary-Thesaurus, or NASA Thesaurus which is available on the WWW at the following URL:<http://www.sti.nasa.gov/thesfrm1.htm>. Each relation is classified under the same relationship category or categories as its synonyms. For example, “works for” is a synonym of “employed by”, and both terms are classified under the “Employment Relationship” (FIG. 5).

The domain knowledge check unit 160 applies domain knowledge to minimize ambiguity in the relations. For example, certain relations can be categorized under several relationships. As an illustration, the term “by” can mean authorship as in “a book ‘by’ author”, or locational proximity as in “a house ‘by’ the lake”. The domain knowledge check unit 160 applies domain knowledge to these phrases to add clarity and distinctiveness to the relation ri of the pair pi. If the second term (B) in the pair pi (A, B) is a person's name, the relation ri is classified under the “Author Relationship”, while if the term (B) identifies a location, such as lake, mountain, street, etc., the relation ri is classified under the “Geographical Relationship”.

If the knowledge module 90 determines that the relation ri has already been categorized under an existing relationship, the knowledge module 90 records the finding in the relationship database 130. In other terms, the knowledge module 90 considers the content of the document di for any indications that would further clarify the relationship being mined.

The statistics module 100 renders statistical judgment of the relation ri on the basis of the frequency of occurrence of the relation ri in the document di. As an example, for the phrase “A by B”, with no other domain knowledge in the document di, the relation ri is classified with the highest frequency of occurrence. If the most frequent use or meaning of the term “by” is or relates to an authorship relationship, the relation ri will be classified under the “Authorship Relationship”. The relation ri will be categorized and stored in the database 130 under one or more relationship categories by the statistics module 100.

The operation of the automatic mining system 10 is represented in FIG. 4 by a process 200. The process 200 starts with the seed pairs Pi−1, and relations Ri−1. At step or block 205, the automatic mining system 10 extracts the pair pi and its associated relation ri to be analyzed from the relations database 80, and inputs the same to the stemming unit 140. At step 210, the stemming unit 140 applies the stemming check to the new relation ri, and proceeds to the decision block 212.

At step 212, the process 200 inquires whether or not the relation ri and its stem (or stems) have already been categorized under the existing relationships in the database 130. If the process 200 determines that the relation ri and its stems have been categorized, it records the finding in the relationship database 130 if the relation ri is new, and terminates the mining progress and returns to block 205 where it extracts another pair pi+1 and relation r1+1. If however, the process 200 determines that at least one of the relation ri or its stems has not been categorized, it proceeds to step 215 where the synonym check unit 150 applies the synonym check to the non-categorized stem of the relation ri, and proceeds to decision block 217.

At step or block 217, the process 200 inquires whether or not the synonym or synonyms of the stem have already been categorized under existing relationships in the database 130. If the process 200 determines that these synonyms have been categorized, it records the finding in the relationship database 130 if the relation ri is new, and terminates the mining progress and returns to block 205 where it extracts another pair pi+1 and relation ri+1. If however, the process 200 determines that at least one of the relation ri, its terms and synonyms has not been categorized, it proceeds to step 220.

At step 220, the domain knowledge check unit 160 applies domain knowledge checking to the non-categorized relation ri, stems, and/or synonyms, and, if needed, generates one or more clarified relations therefrom. The non-categorized relation ri, stems, and/or synonyms, and the clarified relations, if any, will be collectively referred to herein as “clarified relations”. The process 200 then proceeds to the decision block 222 where it inquires whether or not these clarified relations have already been categorized under existing relationships in the database 130. If the process 200 determines that these clarified relations have been categorized, it terminates the mining progress and returns to block 205 where it extracts another pair pi+1 and relation ri+1. If the process 200 determines that the clarified relations form a new instance (or case) of an existing relationship, the domain knowledge check unit 160 records the finding in the relationship database 130.

If the process 200 determines that at least one of the clarified relations has not been categorized, it proceeds to step 225 where the statistics module 100 applies the frequency test to the non-categorized clarified relations, and proceeds to block 230. At block 230, the statistics module 100 stores the non-categorized clarified relations in the relationship database 130 for future use.

It is to be understood that the specific embodiments of the invention that have been described are merely illustrative of certain application of the principles of the present invention. Numerous modifications may be made to automatic mining system and associated methods described herein without departing from the spirit and scope of the present invention. Moreover, while the present invention is described for illustration purpose only in relation to the WWW, it should be clear that the invention is applicable as well to databases and other tables with indexed entries.

Patent Citations
Cited PatentFiling datePublication dateApplicantTitle
US5386556 *23 Dec 199231 Jan 1995International Business Machines CorporationNatural language analyzing apparatus and method
US5418948 *8 Sep 199323 May 1995West Publishing CompanyConcept matching of natural language queries with a database of document concepts
US574536014 Aug 199528 Apr 1998International Business Machines Corp.Dynamic hypertext link converter system and process
US5794050 *2 Oct 199711 Aug 1998Intelligent Text Processing, Inc.Natural language understanding system
US5799268 *28 Sep 199425 Aug 1998Apple Computer, Inc.Method for extracting knowledge from online documentation and creating a glossary, index, help database or the like
US581926022 Jan 19966 Oct 1998Lexis-NexisPhrase recognition method and apparatus
US58571799 Sep 19965 Jan 1999Digital Equipment CorporationComputer method and apparatus for clustering documents and automatic generation of cluster keywords
US6076088 *6 Feb 199713 Jun 2000Paik; WoojinInformation extraction system and method using concept relation concept (CRC) triples
US6182066 *26 Nov 199730 Jan 2001International Business Machines Corp.Category processing of query topics and electronic document content topics
US6185550 *13 Jun 19976 Feb 2001Sun Microsystems, Inc.Method and apparatus for classifying documents within a class hierarchy creating term vector, term file and relevance ranking
US6212494 *20 Jul 19983 Apr 2001Apple Computer, Inc.Method for extracting knowledge from online documentation and creating a glossary, index, help database or the like
US6236991 *26 Nov 199722 May 2001International Business Machines Corp.Method and system for providing access for categorized information from online internet and intranet sources
US6263335 *29 Mar 199917 Jul 2001Textwise LlcInformation extraction system and method using concept-relation-concept (CRC) triples
US6385629 *15 Nov 19997 May 2002International Business Machine CorporationSystem and method for the automatic mining of acronym-expansion pairs patterns and formation rules
Non-Patent Citations
Reference
1"Acronym Finder", published on the Word Wide Web at URL:http://acronymfinder.com/ as of Sep. 4, 1999.
2A. Hutchunson, "Metrics on Terms and Clauses," Department of Computer Science, King's College London.
3B. Huberman et al., "Strong Regularities in Word Wide Web Surfing," Xerox Palo Alto Research Center.
4 *Brin, S. "Extracting Patterns and Relations from the World Wide Web", WebDB Workshop at the 6th International Conference on Extending Database Technology, EDBT '98, 1998, 12 pages.*
5 *Brin, S. et al. "Beyond Market Baskets: Generalizing Association Rules to Correlations", Proceedings of the ACM SIGMOD International Conference on Management of Data and Symposium on Principles of Database Systems, 1997, pp. 265-276.*
6 *Coates-Stephens, S. "The Analysis and Acquisition of Proper Names for Robust Text Understanding", Ph. D. thesis, Departme of Computer Science, City University, London, England, Oct. 1992.*
7D. Gibson et al., "Inferring Web Communities from Link Topology," Proceedings of the 9th ACM. Conference on Hypertext and Hypermedia, Pittsburgh, PA, 1998.
8D. Turnbull. "Bibliometrics and the World Wide Web," Technical Report University of Toronto, 1996.
9G. Piatetsky-Shapiro, "Discovery, Analysis, and Presentation of Strong Rules," pp. 229-248.
10G. Plotkin. "A Note Inductive Generalization," pp. 153-163.
11J. Kleinberg, "Authoritative Sources in a Hyperlinked Environment," Proc. of 9th ACM-SIAM Symposium on Discrete Algorithms, May 1997.
12K. McCain, "Mapping Authors in Intellectual Space: A technical Overview," Journal of the American Society for Information Science, 41(6):433-443, 1990.
13 *Liddy, E.D. and Myaeng, S.H. "DR-LINK: A System Update for TREC-2", Proceedings of the 2nd Text REtrieval Conference (TREC-2), 1993, pp. 85-100.*
14 *Liddy, E.D., Paik, W. and Yu, E.S. "Text Categorization for Multiple Users Based on Semantic Features from a Machine-Readable Dictionary", ACM Transactions on Information Systems, vol. 12, No. 3, Jul. 1994, pp. 278-295.*
15 *Martin, P. "Using the WordNet Concept Catalog and a Relation Hierarchy for Knowledge Acquisition", Proceedings of the 4th Peirce Workshop, Aug. 18, 1995.*
16 *Martin, P. and Eklund, P. "Languages and Ontologies to Structure and Access Web Knowledge", 10th Annual ACM Conference on Hypertext and Hypermedia, Feb. 21-25, 1999.*
17 *Paik, W. "Chronological Information Extraction System (CIES)", Syracuse University, undated, 5 pages.*
18R. Agrawal et al., "Fast Algorithms for Mining Association Rules," Proc. of the 20th Int'l Conference on VLDB, Santiago, Chile, Sep. 1994.
19R. Agrawal et al., Mining Association Rules Between Sets of Items in Large Databases, Proceedings of ACM SIGMOD Conference on Management of Data, pp. 207-216, Washington, D.C., May 1993.
20R. Feldman et al., "Mining Associations in Text in the Presence of Background Knowledge," Proceedings of the Second International Conference on Knowledge Discovery and Data Mining, Aug. 2-4, 1996, Portland, Oregon.
21R. Kumar et al., "Trawling the Web for Emerging Cyber-Communities," published on the Word Wide Web at URL: http://www8.org/w8-papers/4a-search-mining/trawling/trawling.html as of Nov. 13, 1999.
22R. Larson, "Bibliometrics of the World Wide Web: An Exploratory Analysis of the Intellectual Structure of Cyberspace," the Proceedings of the 1966 American Society for Information Science Annual Meeting, also published as a technical report, School of Information Management and Systems, University of California, Berkeley, 1996, which is published on the Word Wide Web at URL: http://sherlock.sims.berkeley.edu/docs/asis96/asis96.html.
23R. Miller et al., "SPHINX: A Framework for Creating Personal, Site-specific Web Crawlers," published on the Word Wide Web at URL: http://www.7scu.edu.au/programme/fullpapers/1875/com1875.htm as of Aug. 16, 199.
24R. Srikant et al., "Mining Generalized Association Rules," Proceedings of the 21st VLDB Conference, Zurich, Swizerland, 1995.
25S. Brin, "Extracting Patterns and Relations from the World Wide Web," WebDB, Valencia, Spain, 1998.
26S. Chakrabarti et al. "Focused Crawling: A New Approach to Topic-Specific Web Resource Discovery," Proc. of The 8th International World Wide Web Conference, Toronto, Canada, May 1999.
27S. Soderland. "Learning to Extract Text-based Information from the World Wide Web," American Association for Artificial Intelligence (www.aaai.org), pp. 251-254.
28W. Li et al., "Facilitating comlex Web queries through visual user interfaces and query relaxation," published on the Word Wide Web at URL: http://www.7scu.edu.au/programme/fullpapers/1936/com1936.htm as of Aug. 16, 1999.
Referenced by
Citing PatentFiling datePublication dateApplicantTitle
US6862559 *23 Jul 19991 Mar 2005Xerox CorporationMethods and apparatuses for measuring diversity in combinatorial structures
US6883135 *26 Jun 200019 Apr 2005Microsoft CorporationProxy server using a statistical model
US6978275 *31 Aug 200120 Dec 2005Hewlett-Packard Development Company, L.P.Method and system for mining a document containing dirty text
US69832888 Aug 20013 Jan 2006Cisco Technology, Inc.Multiple layer information object repository
US700701830 Mar 200128 Feb 2006Cisco Technology, Inc.Business vocabulary data storage using multiple inter-related hierarchies
US706270518 Jul 200113 Jun 2006Cisco Technology, Inc.Techniques for forming electronic documents comprising multiple information types
US7103607 *18 Jul 20015 Sep 2006Cisco Technology, Inc.Business vocabulary data retrieval using alternative forms
US71399738 Aug 200121 Nov 2006Cisco Technology, Inc.Dynamic information object cache approach useful in a vocabulary retrieval system
US715205720 Jan 200619 Dec 2006Microsoft CorporationUtilizing information redundancy to improve text searches
US716503623 Oct 200216 Jan 2007Electronic Data Systems CorporationSystem and method for managing a procurement process
US719448319 Mar 200320 Mar 2007Intelligenxia, Inc.Method, system, and computer program product for concept-based multi-dimensional analysis of unstructured information
US7236923 *7 Aug 200226 Jun 2007Itt Manufacturing Enterprises, Inc.Acronym extraction system and method of identifying acronyms and extracting corresponding expansions from text
US7249046 *31 Aug 199924 Jul 2007Fuji Xerox Co., Ltd.Optimum operator selection support system
US732840122 Dec 20045 Feb 2008Microsoft CorporationAdaptive web crawling using a statistical model
US7428517 *27 Feb 200323 Sep 2008Brands Michael Rik FransData integration and knowledge management solution
US749003313 Jan 200510 Feb 2009International Business Machines CorporationSystem for compiling word usage frequencies
US7502836 *8 Nov 200510 Mar 2009Cisco Technology, Inc.System and method for processing a request for information in a network
US75364135 Dec 200519 May 2009Ixreveal, Inc.Concept-based categorization of unstructured objects
US758422118 Mar 20041 Sep 2009Microsoft CorporationField weighting in text searching
US759657431 Aug 200629 Sep 2009Primal Fusion, Inc.Complex-adaptive system for providing a facted classification
US759991715 Aug 20056 Oct 2009Microsoft CorporationRanking search results using biased click distance
US76036165 Nov 200413 Oct 2009Microsoft CorporationProxy server using a statistical model
US760678118 Oct 200620 Oct 2009Primal Fusion Inc.System, method and computer program for facet analysis
US76275883 Oct 20031 Dec 2009Ixreveal, Inc.System and method for concept based analysis of unstructured data
US767648522 Jan 20079 Mar 2010Ixreveal, Inc.Method and computer program product for converting ontologies into concept semantic networks
US768955718 Jul 200530 Mar 2010Madan PanditSystem and method of textual information analytics
US771619821 Dec 200411 May 2010Microsoft CorporationRanking search results using feature extraction
US773927730 Sep 200415 Jun 2010Microsoft CorporationSystem and method for incorporating anchor text into ranking search results
US776144830 Sep 200420 Jul 2010Microsoft CorporationSystem and method for ranking search results using click distance
US778825111 Oct 200631 Aug 2010Ixreveal, Inc.System, method and computer program product for concept-based searching and analysis
US779283326 Apr 20067 Sep 2010Microsoft CorporationRanking search results using language types
US782718129 Sep 20052 Nov 2010Microsoft CorporationClick distance determination
US78315595 Dec 20059 Nov 2010Ixreveal, Inc.Concept-based trends and exceptions tracking
US784056918 Oct 200723 Nov 2010Microsoft CorporationEnterprise relevancy ranking using a neural network
US784909022 Jan 20077 Dec 2010Primal Fusion Inc.System, method and computer program for faceted classification synthesis
US785643412 Nov 200721 Dec 2010Endeca Technologies, Inc.System and method for filtering rules for manipulating search results in a hierarchical search and navigation system
US78608179 Sep 200928 Dec 2010Primal Fusion Inc.System, method and computer program for facet analysis
US786087330 Jul 200428 Dec 2010International Business Machines CorporationSystem and method for automatic terminology discovery
US78905145 Dec 200515 Feb 2011Ixreveal, Inc.Concept-based searching of unstructured objects
US791282331 Oct 200722 Mar 2011Endeca Technologies, Inc.Hierarchical data-driven navigation system and method for information retrieval
US793038920 Nov 200719 Apr 2011The Invention Science Fund I, LlcAdaptive filtering of annotated messages or the like
US796250719 Nov 200714 Jun 2011Microsoft CorporationWeb content mining of pair-based data
US800114426 Mar 200816 Aug 2011International Business Machines CorporationDetecting relationships in unstructured text
US80105704 Jun 200930 Aug 2011Primal Fusion Inc.System, method and computer program for transforming an existing complex data structure to another complex data structure
US801975210 Nov 200513 Sep 2011Endeca Technologies, Inc.System and method for information retrieval from object collections with complex interrelationships
US806540431 Aug 200722 Nov 2011The Invention Science Fund I, LlcLayering destination-dependent content handling guidance
US808222531 Aug 200720 Dec 2011The Invention Science Fund I, LlcUsing destination-dependent criteria to guide data transmission decisions
US80822461 Jul 201020 Dec 2011Microsoft CorporationSystem and method for ranking search results using click distance
US80955655 May 200610 Jan 2012Microsoft CorporationMetadata driven user interface
US810353423 Oct 200224 Jan 2012Hewlett-Packard Development Company, L.P.System and method for managing supplier intelligence
US834653313 Nov 20081 Jan 2013International Business Machines CorporationCompiling word usage frequencies
US8370128 *30 Sep 20085 Feb 2013Xerox CorporationSemantically-driven extraction of relations between named entities
US849500128 Aug 200923 Jul 2013Primal Fusion Inc.Systems and methods for semantic concept definition and semantic concept relationship synthesis utilizing existing domain definitions
US851030231 Aug 200713 Aug 2013Primal Fusion Inc.System, method, and computer program for a consumer defined information architecture
US854337313 Nov 200824 Sep 2013International Business Machines CorporationSystem for compiling word usage frequencies
US858941329 Oct 200319 Nov 2013Ixreveal, Inc.Concept-based method and system for dynamically analyzing results from search engines
US866698313 Jun 20034 Mar 2014Microsoft CorporationArchitecture for generating responses to search engine queries
US86767221 May 200918 Mar 2014Primal Fusion Inc.Method, system, and computer program for user-driven dynamic generation of semantic networks and media synthesis
US867673230 Dec 201118 Mar 2014Primal Fusion Inc.Methods and apparatus for providing information of interest to one or more users
US867680230 Nov 200618 Mar 2014Oracle Otc Subsidiary LlcMethod and system for information retrieval with clustering
US87130539 Mar 201029 Apr 2014Cisco Technology, IncActive tags
US8726144 *23 Dec 200513 May 2014Xerox CorporationInteractive learning-based document annotation
US87386351 Jun 201027 May 2014Microsoft CorporationDetection of junk in search result ranking
US879370616 Dec 201029 Jul 2014Microsoft CorporationMetadata-based eventing supporting operations on data
US881249311 Apr 200819 Aug 2014Microsoft CorporationSearch results ranking using editing distance and document information
US884348629 Sep 200923 Sep 2014Microsoft CorporationSystem and method for scoping searches using index keys
US88498606 Jan 201230 Sep 2014Primal Fusion Inc.Systems and methods for applying statistical inference techniques to knowledge representations
US894301617 Jun 201327 Jan 2015Primal Fusion Inc.Systems and methods for semantic concept definition and semantic concept relationship synthesis utilizing existing domain definitions
US909251620 Jun 201228 Jul 2015Primal Fusion Inc.Identifying information of interest based on user preferences
US909857520 Jun 20124 Aug 2015Primal Fusion Inc.Preference-guided semantic processing
US910477921 Jun 201111 Aug 2015Primal Fusion Inc.Systems and methods for analyzing and synthesizing complex knowledge representations
US917724810 Sep 20123 Nov 2015Primal Fusion Inc.Knowledge representation systems and methods incorporating customization
US923580615 Mar 201312 Jan 2016Primal Fusion Inc.Methods and devices for customizing knowledge representation systems
US924524314 Apr 200926 Jan 2016Ureveal, Inc.Concept-based analysis of structured and unstructured data using concept inheritance
US926252011 May 201116 Feb 2016Primal Fusion Inc.System, method and computer program for creating and manipulating data structures using an interactive graphical interface
US92928558 Sep 200922 Mar 2016Primal Fusion Inc.Synthesizing messaging using context provided by consumers
US934891210 Sep 200824 May 2016Microsoft Technology Licensing, LlcDocument length as a static relevance feature for ranking search results
US936136516 Jun 20117 Jun 2016Primal Fusion Inc.Methods and apparatus for searching of content using semantic synthesis
US93742428 Nov 200721 Jun 2016Invention Science Fund I, LlcUsing evaluations of tentative message content
US937820330 Dec 201128 Jun 2016Primal Fusion Inc.Methods and apparatus for providing information of interest to one or more users
US949546227 Jan 201215 Nov 2016Microsoft Technology Licensing, LlcRe-ranking search results
US95762417 Dec 201521 Feb 2017Primal Fusion Inc.Methods and devices for customizing knowledge representation systems
US959500416 Dec 201414 Mar 2017Primal Fusion Inc.Systems and methods for semantic concept definition and semantic concept relationship synthesis utilizing existing domain definitions
US97155523 Jun 201525 Jul 2017Primal Fusion Inc.Techniques for presenting content to a user based on the user's preferences
US97812123 Nov 20163 Oct 2017mBLAST, Inc.Method and apparatus for collecting and disseminating information over a computer network
US9792351 *10 Jun 200517 Oct 2017International Business Machines CorporationTolerant and extensible discovery of relationships in data using structural information and data analysis
US979255026 May 201617 Oct 2017Primal Fusion Inc.Methods and apparatus for providing information of interest to one or more users
US20020051020 *21 Sep 20012 May 2002Adam FerrariScalable hierarchical data-driven navigation system and method for information retrieval
US20030046263 *31 Aug 20016 Mar 2003Maria CastellanosMethod and system for mining a document containing dirty text
US20030115080 *23 Oct 200219 Jun 2003Kasra KasraviSystem and method for managing contracts using text mining
US20030120477 *23 Oct 200226 Jun 2003Kruk Jeffrey M.System and method for managing a procurement process
US20030120504 *23 Oct 200226 Jun 2003Kruk Jeffrey M.System and method for managing supplier intelligence
US20030130878 *23 Oct 200210 Jul 2003Kruk Jeffrey M.System and method for managing spending
US20040010483 *27 Feb 200315 Jan 2004Brands Michael Rik FransData integration and knowledge management solution
US20040117366 *12 Dec 200217 Jun 2004Ferrari Adam J.Method and system for interpreting multiple-term queries
US20040167907 *5 Dec 200326 Aug 2004Attensity CorporationVisualization of integrated structured data and extracted relational facts from free text
US20040167911 *5 Dec 200326 Aug 2004Attensity CorporationMethods and products for integrating mixed format data including the extraction of relational facts from free text
US20040254917 *13 Jun 200316 Dec 2004Brill Eric D.Architecture for generating responses to search engine queries
US20050038781 *8 Sep 200317 Feb 2005Endeca Technologies, Inc.Method and system for interpreting multiple-term queries
US20050086583 *5 Nov 200421 Apr 2005Microsoft CorporationProxy server using a statistical model
US20050165778 *22 Dec 200428 Jul 2005Microsoft CorporationAdaptive Web crawling using a statistical model
US20050210006 *18 Mar 200422 Sep 2005Microsoft CorporationField weighting in text searching
US20060053104 *8 Nov 20059 Mar 2006Endeca Technologies, Inc.Hierarchical data-driven navigation system and method for information retrieval
US20060069982 *29 Sep 200530 Mar 2006Microsoft CorporationClick distance determination
US20060074871 *30 Sep 20046 Apr 2006Microsoft CorporationSystem and method for incorporating anchor text into ranking search results
US20060074903 *30 Sep 20046 Apr 2006Microsoft CorporationSystem and method for ranking search results using click distance
US20060116996 *20 Jan 20061 Jun 2006Microsoft CorporationUtilizing information redundancy to improve text searches
US20060136147 *15 Dec 200522 Jun 2006Hyun-Chul JangBiological relationship event extraction system and method for processing biological information
US20060136411 *21 Dec 200422 Jun 2006Microsoft CorporationRanking search results using feature extraction
US20060155539 *13 Jan 200513 Jul 2006Yen-Fu ChenSystem for compiling word usage frequencies
US20060200460 *3 Mar 20057 Sep 2006Microsoft CorporationSystem and method for ranking search results using file types
US20060277465 *18 Jul 20057 Dec 2006Textual Analytics Solutions Pvt. Ltd.System and method of textual information analytics
US20060282429 *10 Jun 200514 Dec 2006International Business Machines CorporationTolerant and extensible discovery of relationships in data using structural information and data analysis
US20060294100 *26 Apr 200628 Dec 2006Microsoft CorporationRanking search results using language types
US20070038622 *15 Aug 200515 Feb 2007Microsoft CorporationMethod ranking search results using biased click distance
US20070067320 *20 Sep 200522 Mar 2007International Business Machines CorporationDetecting relationships in unstructured text
US20070106658 *10 Nov 200510 May 2007Endeca Technologies, Inc.System and method for information retrieval from object collections with complex interrelationships
US20070118542 *22 Jan 200724 May 2007Peter SweeneySystem, Method and Computer Program for Faceted Classification Synthesis
US20070130205 *5 May 20067 Jun 2007Microsoft CorporationMetadata driven user interface
US20070136221 *18 Oct 200614 Jun 2007Peter SweeneySystem, Method and Computer Program for Facet Analysis
US20070150801 *23 Dec 200528 Jun 2007Xerox CorporationInteractive learning-based document annotation
US20070192272 *22 Jan 200716 Aug 2007Intelligenxia, Inc.Method and computer program product for converting ontologies into concept semantic networks
US20080021925 *31 Aug 200624 Jan 2008Peter SweeneyComplex-adaptive system for providing a faceted classification
US20080059442 *31 Aug 20076 Mar 2008International Business Machines CorporationSystem and method for automatically expanding referenced data
US20080065603 *11 Oct 200613 Mar 2008Robert John CarlsonSystem, method & computer program product for concept-based searching & analysis
US20080133479 *30 Nov 20065 Jun 2008Endeca Technologies, Inc.Method and system for information retrieval with clustering
US20080134100 *31 Oct 20075 Jun 2008Endeca Technologies, Inc.Hierarchical data-driven navigation system and method for information retrieval
US20080177740 *26 Mar 200824 Jul 2008International Business Machines CorporationDetecting relationships in unstructured text
US20090063478 *13 Nov 20085 Mar 2009International Business Machines CorporationSystem for Compiling Word Usage Frequencies
US20090063483 *13 Nov 20085 Mar 2009Inernational Business Machines CorporationSystem for Compiling Word Usage Frequencies
US20090063518 *31 Aug 20075 Mar 2009Searete Llc, A Limited Liability Corporation Of The State Of DelawareUsing destination-dependent criteria to guide data transmission decisions
US20090106221 *18 Oct 200723 Apr 2009Microsoft CorporationRanking and Providing Search Results Based In Part On A Number Of Click-Through Features
US20090106223 *18 Oct 200723 Apr 2009Microsoft CorporationEnterprise relevancy ranking using a neural network
US20090106235 *10 Sep 200823 Apr 2009Microsoft CorporationDocument Length as a Static Relevance Feature for Ranking Search Results
US20090132530 *19 Nov 200721 May 2009Microsoft CorporationWeb content mining of pair-based data
US20090259651 *11 Apr 200815 Oct 2009Microsoft CorporationSearch results ranking using editing distance and document information
US20090300326 *4 Jun 20093 Dec 2009Peter SweeneySystem, method and computer program for transforming an existing complex data structure to another complex data structure
US20090313332 *31 Aug 200717 Dec 2009Searete Llc, A Limited Liability Corporation Of The State Of DelawareLayering destination-dependent content handling guidance
US20100017403 *29 Sep 200921 Jan 2010Microsoft CorporationSystem and method for scoping searches using index keys
US20100036790 *9 Sep 200911 Feb 2010Primal Fusion, Inc.System, method and computer program for facet analysis
US20100049766 *31 Aug 200725 Feb 2010Peter SweeneySystem, Method, and Computer Program for a Consumer Defined Information Architecture
US20100057664 *28 Aug 20094 Mar 2010Peter SweeneySystems and methods for semantic concept definition and semantic concept relationship synthesis utilizing existing domain definitions
US20100082331 *30 Sep 20081 Apr 2010Xerox CorporationSemantically-driven extraction of relations between named entities
US20100235307 *1 May 200916 Sep 2010Peter SweeneyMethod, system, and computer program for user-driven dynamic generation of semantic networks and media synthesis
US20100262620 *14 Apr 200914 Oct 2010Rengaswamy MohanConcept-based analysis of structured and unstructured data using concept inheritance
US20110060644 *8 Sep 200910 Mar 2011Peter SweeneySynthesizing messaging using context provided by consumers
US20110060645 *8 Sep 200910 Mar 2011Peter SweeneySynthesizing messaging using context provided by consumers
US20110060794 *8 Sep 200910 Mar 2011Peter SweeneySynthesizing messaging using context provided by consumers
US20110213763 *4 May 20111 Sep 2011Microsoft CorporationWeb content mining of pair-based data
US20110225193 *9 Mar 201015 Sep 2011Jennings Cullen FActive tags
US20120029908 *20 Jul 20112 Feb 2012Shingo TakamatsuInformation processing device, related sentence providing method, and program
Classifications
U.S. Classification1/1, 704/9, 707/E17.09, 707/E17.084, 707/E17.107, 707/999.005, 707/999.01
International ClassificationG06F17/30
Cooperative ClassificationY10S707/99935, G06F17/30861, G06F17/30707, G06F17/30616
European ClassificationG06F17/30T1E, G06F17/30W, G06F17/30T4C
Legal Events
DateCodeEventDescription
15 Nov 1999ASAssignment
Owner name: INTERNATIONAL BUSINESS MACHINES CORPORATION, NEW Y
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:SUNDARESAN, NEELAKANTAN;YI, JEONGHEE;REEL/FRAME:010400/0034
Effective date: 19991115
30 Jun 2006FPAYFee payment
Year of fee payment: 4
16 Jul 2010FPAYFee payment
Year of fee payment: 8
31 Oct 2014REMIMaintenance fee reminder mailed
25 Mar 2015LAPSLapse for failure to pay maintenance fees
12 May 2015FPExpired due to failure to pay maintenance fee
Effective date: 20150325